Towards capturing and preserving changes on the Web of Data. Umbrich, J., Mrzelj, N., & Polleres, A. In Managing the Evolution and Preservation of the Data Web - First Diachron Workshop at ESWC 2015, pages 50–65, Portorož, Slovenia, May, 2015. Paper abstract bibtex Existing Web archives aim to capture and preserve the changes of documents on the Web and provide data corpora of high value which are used in various areas (e.g. to optimise algorithms or to study the Zeitgeist of a generation). So far, the Web archives concentrate their efforts to capture the large Web of documents with periodic snapshot crawls. Little focus is drawn to preserve the continuously growing Web of Data and actually keeping track of the real frequency of changes. In this work we present our efforts to capture and archive the changes on the Web of Data. We describe our infrastructure and focus on evaluating strategies to accurately capture the changes of data and to also estimate the crawl time for a given set of URLs with the aim to optimally schedule the revising of URLs with limited resources.
@inproceedings{umbr-etal-2015diachron,
author = {J\"urgen Umbrich and Nina Mrzelj and Axel Polleres},
title = {Towards capturing and preserving changes on the Web of Data},
booktitle = {Managing the Evolution and Preservation of the Data Web - First Diachron Workshop at ESWC 2015},
year = 2015,
abstract = {Existing Web archives aim to capture and preserve the changes
of documents on the Web and provide data corpora of high value which
are used in various areas (e.g. to optimise algorithms or to study
the Zeitgeist of a generation). So far, the Web archives concentrate their efforts
to capture the large Web of documents with periodic snapshot crawls.
Little focus is drawn to preserve the continuously growing Web of Data
and actually keeping track of the real frequency of changes. In this work
we present our efforts to capture and archive the changes on the Web of
Data. We describe our infrastructure and focus on evaluating strategies
to accurately capture the changes of data and to also estimate the crawl
time for a given set of URLs with the aim to optimally schedule the
revising of URLs with limited resources.},
address = {Portoro{\v{z}}, Slovenia},
month = may,
day = 31,
pages = {50--65},
url = {http://ceur-ws.org/Vol-1377/paper7.pdf},
}
Downloads: 0
{"_id":"tKrdLZty3MXkqQDpr","bibbaseid":"umbrich-mrzelj-polleres-towardscapturingandpreservingchangesonthewebofdata-2015","downloads":0,"creationDate":"2015-12-08T08:58:02.544Z","title":"Towards capturing and preserving changes on the Web of Data","author_short":["Umbrich, J.","Mrzelj, N.","Polleres, A."],"year":2015,"bibtype":"inproceedings","biburl":"www.polleres.net/mypublications.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Jürgen"],"propositions":[],"lastnames":["Umbrich"],"suffixes":[]},{"firstnames":["Nina"],"propositions":[],"lastnames":["Mrzelj"],"suffixes":[]},{"firstnames":["Axel"],"propositions":[],"lastnames":["Polleres"],"suffixes":[]}],"title":"Towards capturing and preserving changes on the Web of Data","booktitle":"Managing the Evolution and Preservation of the Data Web - First Diachron Workshop at ESWC 2015","year":"2015","abstract":"Existing Web archives aim to capture and preserve the changes of documents on the Web and provide data corpora of high value which are used in various areas (e.g. to optimise algorithms or to study the Zeitgeist of a generation). So far, the Web archives concentrate their efforts to capture the large Web of documents with periodic snapshot crawls. Little focus is drawn to preserve the continuously growing Web of Data and actually keeping track of the real frequency of changes. In this work we present our efforts to capture and archive the changes on the Web of Data. We describe our infrastructure and focus on evaluating strategies to accurately capture the changes of data and to also estimate the crawl time for a given set of URLs with the aim to optimally schedule the revising of URLs with limited resources.","address":"Portorož, Slovenia","month":"May","day":"31","pages":"50–65","url":"http://ceur-ws.org/Vol-1377/paper7.pdf","bibtex":"@inproceedings{umbr-etal-2015diachron,\nauthor = {J\\\"urgen Umbrich and Nina Mrzelj and Axel Polleres},\ntitle = {Towards capturing and preserving changes on the Web of Data},\nbooktitle = {Managing the Evolution and Preservation of the Data Web - First Diachron Workshop at ESWC 2015},\nyear = 2015,\nabstract = {Existing Web archives aim to capture and preserve the changes\nof documents on the Web and provide data corpora of high value which\nare used in various areas (e.g. to optimise algorithms or to study \nthe Zeitgeist of a generation). So far, the Web archives concentrate their efforts\nto capture the large Web of documents with periodic snapshot crawls.\nLittle focus is drawn to preserve the continuously growing Web of Data\nand actually keeping track of the real frequency of changes. In this work\nwe present our efforts to capture and archive the changes on the Web of\nData. We describe our infrastructure and focus on evaluating strategies\nto accurately capture the changes of data and to also estimate the crawl\ntime for a given set of URLs with the aim to optimally schedule the\nrevising of URLs with limited resources.},\naddress = {Portoro{\\v{z}}, Slovenia},\nmonth = may,\nday = 31,\npages = {50--65},\nurl = {http://ceur-ws.org/Vol-1377/paper7.pdf},\n}\n\n","author_short":["Umbrich, J.","Mrzelj, N.","Polleres, A."],"key":"umbr-etal-2015diachron","id":"umbr-etal-2015diachron","bibbaseid":"umbrich-mrzelj-polleres-towardscapturingandpreservingchangesonthewebofdata-2015","role":"author","urls":{"Paper":"http://ceur-ws.org/Vol-1377/paper7.pdf"},"metadata":{"authorlinks":{"polleres, a":"https://bibbase.org/show?bib=www.polleres.net/mypublications.bib"}},"downloads":0,"html":""},"search_terms":["towards","capturing","preserving","changes","web","data","umbrich","mrzelj","polleres"],"keywords":[],"authorIDs":["545720922abc8e9f370000ae","5PFMiHGwfvbGBZwWF","5de7280d97054edf010000c3","5e02b1a419da8edf01000028","5e048450db7916df010000b1","5e06d565a0810cde0100009b","5e10e27445c12cde01000062","5e123345c196d3de01000074","5e14ba61e55ed8de01000072","5e189b4e779abfdf0100013f","5e216f7e5a651cdf010000eb","5e25b9fdf299d4de01000001","5e2d64605e7586df01000083","5e36e5e9b26a0fde0100005e","5e37d23b56571fde010000de","5e4ded1052c311f20100018e","5e51a3102793ecde010000e0","5e59a6b5ad6c7fde01000114","5e5d588ead47bcde01000072","5e60e857839e59df010000f1","A5AFuDAiNR4HEYiFD","BtzwZ6TFPsASbdqvo","DLdeXAmrbA4niYQzH","FyLDFGg993nDS2Spf","NCjPvWahWRjdP3ghB","XcyP3jptz7zE4ZLws","aiXjXMLP63k5WCt84","fTDcT5K3oSTcdxSBj","fbKNfWffDzdzubrER","haaAs2rQaQA7EaZva","nQX2P8WzFeKwcpLqd","nuWuyLnGu7YzMrn4d","pfENTBFWo85mRy3ik","rX6EShFR2rMFmQL2C","w6wHZukTjqqera7BR","woa42kCD35yCmdQTj","yPgvarsL7KAT9yfZd","yzkCNJMYNL8B3bni2","zDG3tj87ZfYXo7u9c"],"dataSources":["cBfwyqsLFQQMc4Fss","gixxkiKt6rtWGoKSh","QfLT6siHZuHw9MqvK"]}